LSTM pour prédire l'onde sinusoïdale

Question

Ici, je voudrais générer un tutoriel d'utilisation de LSTM dans MxNet, avec l'exemple de Tensorflow. (Emplacement https://github.com/mouradmourafiq/tensorflow-lstm-regression/blob/master/lstm_sin.ipynb " Voici mon code majeur

import mxnet as mx 
import numpy as np 
import pandas as pd 
import argparse 
import os 
import sys 
from data_processing import generate_data 
import logging 
head = '%(asctime)-15s %(message)s' 
logging.basicConfig(level=logging.DEBUG, format=head) 
TIMESTEPS = 3 
BATCH_SIZE = 100 
X, y = generate_data(np.sin, np.linspace(0, 100, 10000), TIMESTEPS, seperate=False) 
train_iter = mx.io.NDArrayIter(X['train'], y['train'], batch_size=BATCH_SIZE, shuffle=True, label_name='lro_label') 
eval_iter = mx.io.NDArrayIter(X['val'], y['val'], batch_size=BATCH_SIZE, shuffle=False) 
test_iter = mx.io.NDArrayIter(X['test'], batch_size=BATCH_SIZE, shuffle=False) 
num_layers = 3 
num_hidden = 50 

data = mx.sym.Variable('data') 
label = mx.sym.Variable('lro_label') 

stack = mx.rnn.SequentialRNNCell() 
for i in range(num_layers): 
    stack.add(mx.rnn.LSTMCell(num_hidden=num_hidden, prefix='lstm_l%d_'%i)) 
#stack.reset() 
outputs, states = stack.unroll(length=TIMESTEPS, 
           inputs=data, 
           layout='NTC', 
           merge_outputs=True) 

outputs = mx.sym.reshape(outputs, shape=(BATCH_SIZE, -1)) 
# purpose of fc1 was to make shape change to (batch_size, *), or label shape won't match LSTM unrolled output shape. 
outputs = mx.sym.FullyConnected(data=outputs, num_hidden=1, name='fc1') 
label = mx.sym.reshape(label, shape=(-1,)) 
outputs = mx.sym.LinearRegressionOutput(data=outputs, 
           label=label, 
           name='lro') 
contexts = mx.cpu(0) 
model = mx.mod.Module(symbol = outputs, 
        data_names = ['data'], 
        label_names = ['lro_label']) 
model.fit(train_iter, eval_iter, 
     optimizer_params = {'learning_rate':0.005}, 
     num_epoch=4, 
     batch_end_callback=mx.callback.Speedometer(BATCH_SIZE, 2)) 

Ce code se exécute mais le train_accuracy est Nan. La question est de savoir comment la rendre correcte? Et puisque la forme déroula en a sequence_length, comment peut-il correspondre étiqueter la forme? est-ce que mon sens net de faire FC1?

Answer 1

passe auto_reset=False-Speedometer rappel, par exemple, batch_end_callback=mx.callback.Speedometer(BATCH_SIZE, 2, auto_reset=False), devrait fixer le NaN train acc.